Model Context Protocol moderate risk

Amazon Bedrock

This MCP server provides AI image generation using Amazon Bedrock's Nova Canvas model, offering configurable image parameters and negative prompting.

Connections & Capabilities

Connects To

GitHubAWS

Capabilities

write

Quickstart

Install

npm install
npm

Config

{
  "mcpServers": {
    "amazon-bedrock": {
      "command": "npx",
      "args": [
        "-y",
        "@zxkane/mcp-server-amazon-bedrock"
      ],
      "env": {
        "AWS_PROFILE": "your_profile_name",         // Optional, only if you want to use a specific profile
        "AWS_ACCESS_KEY_ID": "your_access_key",     // Optional if using AWS credentials file or IAM role
        "AWS_SECRET_ACCESS_KEY": "your_secret_key", // Optional if using AWS credentials file or IAM role
        "AWS_REGION": "us-east-1"                   // Optional, defaults to 'us-east-1'
      }
    }
  }
}

Exposed MCP Tools (1)

moderate

generate_image

Generates images from a text prompt using Amazon Bedrock's Nova Canvas model.

Generates images, which consumes resources and could be misused with malicious prompts.

Safety Assessment

The server is relatively safe for generating images within the constraints of the Bedrock service. However, proper AWS credential management is crucial, and monitoring resource consumption is recommended to prevent unexpected costs. Prompt injection risks should be considered.

Image generation is sandboxed within the Bedrock service.
Input validation is performed on parameters.
No direct filesystem access.
Limited write operations (image generation only).

Requires AWS credentials with Bedrock access, which could be misused if compromised.
Image generation can be resource-intensive, potentially leading to cost overruns.
Prompt injection vulnerabilities could lead to unexpected image outputs.
No explicit rate limiting is mentioned, increasing the risk of abuse.